DeepAI AI Chat
Log In Sign Up

Proper Reuse of Image Classification Features Improves Object Detection

by   Cristina Vasconcelos, et al.

A common practice in transfer learning is to initialize the downstream model weights by pre-training on a data-abundant upstream task. In object detection specifically, the feature backbone is typically initialized with Imagenet classifier weights and fine-tuned on the object detection task. Recent works show this is not strictly necessary under longer training regimes and provide recipes for training the backbone from scratch. We investigate the opposite direction of this end-to-end training trend: we show that an extreme form of knowledge preservation – freezing the classifier-initialized backbone – consistently improves many different detection models, and leads to considerable resource savings. We hypothesize and corroborate experimentally that the remaining detector components capacity and structure is a crucial factor in leveraging the frozen backbone. Immediate applications of our findings include performance improvements on hard cases like detection of long-tail object classes and computational and memory resource savings that contribute to making the field more accessible to researchers with access to fewer computational resources.


page 1

page 2

page 3

page 4


Exploring Plain Vision Transformer Backbones for Object Detection

We explore the plain, non-hierarchical Vision Transformer (ViT) as a bac...

DetNet: A Backbone network for Object Detection

Recent CNN based object detectors, no matter one-stage methods like YOLO...

An Analysis of Pre-Training on Object Detection

We provide a detailed analysis of convolutional neural networks which ar...

GiraffeDet: A Heavy-Neck Paradigm for Object Detection

In conventional object detection frameworks, a backbone body inherited f...

Mind the Backbone: Minimizing Backbone Distortion for Robust Object Detection

Building object detectors that are robust to domain shifts is critical f...

Delving into the Pre-training Paradigm of Monocular 3D Object Detection

The labels of monocular 3D object detection (M3OD) are expensive to obta...

Prime Sample Attention in Object Detection

It is a common paradigm in object detection frameworks to treat all samp...